CN117557067B - Distributed energy collaborative optimization system - Google Patents
Distributed energy collaborative optimization system Download PDFInfo
- Publication number
- CN117557067B CN117557067B CN202410032009.4A CN202410032009A CN117557067B CN 117557067 B CN117557067 B CN 117557067B CN 202410032009 A CN202410032009 A CN 202410032009A CN 117557067 B CN117557067 B CN 117557067B
- Authority
- CN
- China
- Prior art keywords
- energy
- configuration
- unit
- optimal
- energy configuration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 55
- 230000010355 oscillation Effects 0.000 claims abstract description 71
- 238000010276 construction Methods 0.000 claims abstract description 5
- 230000000737 periodic effect Effects 0.000 claims description 33
- 230000036962 time dependent Effects 0.000 claims description 21
- 230000006399 behavior Effects 0.000 claims description 13
- 238000013016 damping Methods 0.000 claims description 7
- 239000012467 final product Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 17
- 230000000694 effects Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 230000005855 radiation Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004146 energy storage Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/101—Collaborative creation, e.g. joint development of products or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Feedback Control In General (AREA)
Abstract
The invention belongs to the technical field of energy control, and particularly relates to a distributed energy collaborative optimization system. The system comprises: a plurality of energy units, each configured with a distributed optimization device; the distributed optimization apparatus includes: the system comprises an energy unit model initializing unit, an objective function constructing unit, a collaborative optimizing unit and an adjusting optimizing unit; the energy unit model initialization unit is used for setting an initialization model for the energy unit; the objective function construction unit is used for constructing an objective function; the collaborative optimization unit is used for traversing all possible energy configurations and calculating the performance scores of the energy units under each energy configuration; the adjusting and optimizing unit is used for simulating the periodicity and dynamic change of each energy unit in the system by adding an oscillation item to obtain the final optimal energy configuration. The invention improves the efficiency, the sustainability and the adaptability of energy configuration through the technologies of dynamic adjustment, adaptive enhancement and the like.
Description
Technical Field
The invention belongs to the technical field of energy control, and particularly relates to a distributed energy collaborative optimization system.
Background
Distributed energy systems play an increasingly important role in modern society, they can more efficiently utilize renewable energy, increase energy utilization, and reduce reliance on traditional energy. However, the complexity and dynamics of distributed energy systems make optimizing their performance a challenging task. The present background art introduces existing distributed energy optimization techniques and problems therein, and introduces a new inventive patent technology to solve these problems.
Distributed energy systems are complex networks of multiple energy units, which may be solar cells, wind turbines, energy storage devices, etc. They produce and store energy in a decentralized manner, providing renewable energy sources for the power network. However, due to the uncertainty and dynamics of these energy units, the performance of the distributed energy system is affected by a variety of factors, including weather, load changes, equipment failure, and the like.
The prior art often fails to meet the requirements of system dynamics. Distributed energy systems face many variations, such as changes in weather conditions, energy demands, and equipment status. Conventional approaches often fail to adjust the energy configuration in time to accommodate these changes, resulting in reduced system performance. Conventional approaches have limitations in terms of maximizing performance. They typically employ static models to optimize energy configurations without taking into account the effects of time-dependent and periodic variations on performance. This results in failure to achieve maximization of system performance. In distributed energy systems, optimization of configuration parameters is a complex problem. Different energy units have different configuration parameters and performance characteristics, so finding optimal configuration parameters is challenging. Conventional approaches often lack the adaptability of the system to environmental and demand changes. The energy systems need to be able to flexibly adjust the configuration to changing conditions, whereas the prior art does not provide sufficient flexibility.
Disclosure of Invention
The invention mainly aims to provide a distributed energy collaborative optimization system, which improves the efficiency, the sustainability and the adaptability of energy configuration through dynamic adjustment, adaptive enhancement and other technologies.
In order to solve the technical problems, the invention adopts the following technical scheme:
there is provided a distributed energy co-optimization system, the system comprising: a plurality of energy units, each configured with a distributed optimization device; the distributed optimization apparatus includes: the system comprises an energy unit model initializing unit, an objective function constructing unit, a collaborative optimizing unit and an adjusting optimizing unit; the energy unit model initialization unit is used for setting an initialization model for the energy units, and the initialization model of each energy unit characterizes the initial energy configuration of the energy unit; the objective function construction unit is used for constructing an objective function, calculating the performance score of the energy unit according to the initial state of the energy unit, and taking the performance score as the objective of the objective function; the collaborative optimization unit is used for traversing all possible energy configurations, calculating the performance scores of the energy units under each energy configuration, determining the energy configuration corresponding to the energy unit when the performance scores are optimal, serving as the optimal energy configuration of the energy unit, adjusting the current energy configuration according to the optimal energy configuration, reducing the difference between the performance scores of each current energy configuration and the optimal energy configuration, and completing the first-stage optimization; the adjustment optimizing unit is used for introducing time-dependent dynamic behaviors, simulating the periodicity and dynamic changes of each energy unit in the system by adding oscillation items to obtain dynamic results, performing random search on the dynamic results, calculating to find new optimal energy configuration, adjusting the new optimal energy configuration by using a spiral model to obtain final optimal energy configuration, and updating the optimal energy configuration into the final optimal energy configuration.
Further, the energy source is configured as a data set comprising a plurality of different categories of configuration parameters.
Further, the initialization model of the energy unitThe expression is used as follows:
；
wherein,indicate->The initialization model of each energy unit characterizes the initial energy configuration of the energy unit; />Is a time variable; />A weighted value representing a minimum set of parameters of the energy configuration of the energy unit; />A weighted value representing a maximum set of parameters of the energy configuration of the energy unit; the energy source configuration of each energy source unit is provided with a weighting coefficient matched with the energy source unit corresponding to each category of parameters; weighting value of maximum parameter set of energy configuration +.>Each maximum parameter in the maximum parameter set equal to the energy configuration is multiplied by a corresponding weighting coefficient to obtain a weighting value, and then the weighting values corresponding to all other maximum parameters are added and calculated; weighting value of minimum parameter set of energy configuration +.>Each minimum parameter in the minimum parameter set equal to the energy configuration is multiplied by the corresponding weighting coefficient to obtain a weighting value, then adding the weighted values corresponding to all other minimum parameters, and calculating to obtain the final product; />For generating a random number between 0 and 1, introducing randomness of the initial state; />Representing the influence of a periodic factor, +.>For amplitude, the intensity of the periodicity factor, +.>For frequency +.>For the phase, determining a point in time at which a periodic factor begins to affect the system; />Representing a nonlinear decay term for modeling thermodynamic and mechanical property changes of a system, wherein +.>An initial intensity representing a nonlinear decay; />Indicating the rate of decay; />And->Are index of subscripts, and->For the total number of periodic factors>Is the total number of nonlinear decay terms.
Further, the objective function is expressed using the following formula:
；
wherein,indicate->An objective function of the individual energy units having a value of +.>Performance scores for individual energy units; />Indicate->The individual energy units use->The energy source is configured at the time->The output of the energy source; />Is an attenuation factor; />Represents a penalty function when->If any configuration parameter in the energy configuration does not meet the corresponding set threshold range, calculating the minimum difference value between the configuration parameter and the threshold range by the punishment function, and then calculating the ratio of the minimum difference value to the configuration parameter; />Representing the time-varying frequency, and representing the time-varying threshold range.
Further, the collaborative optimization unit traverses all possible energy configurations by adopting the following formula, calculates the performance scores of the energy units under each energy configuration, and when the performance scores are determined to be optimal, uses the energy configuration corresponding to the energy unit as the optimal energy configuration of the energy unit:
；
wherein,representing an optimal energy configuration; />Indicate->Weights for a range of thresholds; />Indicate->Midpoint values of the respective threshold ranges; />The number of threshold ranges is equal to the number of types of configuration parameters in the energy configuration.
Further, the collaborative optimization unit calculates a difference between the performance scores of the current energy configuration and the optimal energy configuration by adopting the following formula:
；
wherein,indicate->Personal energy configuration and optimal energy configuration +.>A gap between performance scores; />The value range is 1 to 1.3 for the system coefficient; />Is a second order Manhattan norm; />Is a first order Manhattan norm;is->Target values for the respective threshold ranges; by adjusting the current energy configurations, the gap between the performance scores of each current energy configuration and the optimal energy configuration is reducedUp to the difference->Cannot be reduced, and the first-stage optimization is completed.
Furthermore, the adjustment optimizing unit uses the following formula to introduce time-dependent dynamic behavior, and the periodicity and dynamic change of each energy unit in the system are simulated by adding oscillation items to obtain dynamic results：
；
Wherein,system coefficients for controlling step size; />Is the intensity of oscillation; />Is the frequency of oscillation; />Is the initial phase of oscillation; />Is the damping coefficient of the oscillation.
Further, the adjustment optimizing unit performs random search on the intermediate result by using the following formula, calculates to find a new optimal energy configuration：
；
Wherein,is indicated at->And->Generating a random configuration therebetween; />Is an adjustment factor; />Is a time decay coefficient; />Is the time frequency.
Further, the adjustment optimizing unit adjusts the new optimal energy configuration by using a spiral model by using the following formula to obtain a final optimal energy configuration, and updates the optimal energy configuration to the final optimal energy configuration:
；
wherein,configuring the final optimal energy source; />For the current energy allocation and the optimal energy allocation +.>Is a difference between the initial gap of (2); />An expansion factor that is a spiral shape; />Representing a periodic portion of the spiral path;is the phase of the spiral path; />Is the length of the spiral path; />Is the expansion rate of the helical path.
The distributed energy collaborative optimization system has the following beneficial effects: the invention realizes the dynamic adjustment of the energy configuration by introducing time-dependent dynamic behaviors and spiral models into the adjustment optimizing unit. The system can automatically adjust the energy distribution according to the real-time situation so as to adapt to the continuously changing environment and requirements. This enhances the adaptability of the system and helps to improve the robustness and reliability of the system. The objective function construction method of the present invention takes into account time-dependent and periodic variations to achieve maximization of performance. This means that the system can optimize performance in different time periods, better adapting to the actual operating conditions of the system. Maximizing performance helps to improve the efficiency and sustainability of the energy system. The invention introduces the collaborative optimization unit, and can make the decision of the energy configuration jointly participated among different energy units so as to realize the maximization of the performance. The process searches the optimal energy configuration through a plurality of iterations, and ensures that the system can realize the optimal performance under various conditions. Compared with the traditional method, the collaborative optimization method can remarkably improve the efficiency and the sustainability of the distributed energy system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic device structure diagram of a distributed optimization device of a distributed energy collaborative optimization system according to an embodiment of the present invention.
Detailed Description
The method of the present invention will be described in further detail with reference to the accompanying drawings.
Example 1: referring to fig. 1, a distributed energy co-optimization system, the system comprising: a plurality of energy units, each configured with a distributed optimization device; the distributed optimization apparatus includes: the system comprises an energy unit model initializing unit, an objective function constructing unit, a collaborative optimizing unit and an adjusting optimizing unit; the energy unit model initialization unit is used for setting an initialization model for the energy units, and the initialization model of each energy unit characterizes the initial energy configuration of the energy unit; the objective function construction unit is used for constructing an objective function, calculating the performance score of the energy unit according to the initial state of the energy unit, and taking the performance score as the objective of the objective function; the collaborative optimization unit is used for traversing all possible energy configurations, calculating the performance scores of the energy units under each energy configuration, determining the energy configuration corresponding to the energy unit when the performance scores are optimal, serving as the optimal energy configuration of the energy unit, adjusting the current energy configuration according to the optimal energy configuration, reducing the difference between the performance scores of each current energy configuration and the optimal energy configuration, and completing the first-stage optimization; the adjustment optimizing unit is used for introducing time-dependent dynamic behaviors, simulating the periodicity and dynamic changes of each energy unit in the system by adding oscillation items to obtain dynamic results, performing random search on the dynamic results, calculating to find new optimal energy configuration, adjusting the new optimal energy configuration by using a spiral model to obtain final optimal energy configuration, and updating the optimal energy configuration into the final optimal energy configuration.
In particular, the core idea of the spiral model is to simulate the periodic and dynamic changes of the energy unit. In energy systems, many factors may lead to changes in energy demand or production, such as weather, load changes, etc. The spiral model enables the system to simulate these periodic and dynamic changes by introducing an oscillation term. The oscillation term is a mathematical term that periodically increases or decreases the energy configuration to simulate fluctuations in an actual system. The design of the oscillation term may be based on known periodic factors, such as daily solar radiation changes or hourly power demand fluctuations. The name of the spiral model derives from its mode of motion. The introduction of the oscillation term causes the energy configuration to exhibit a trend in the spiral shape in the performance score and objective function, similar to the movement of a spiral. The spiral shape changes make the system more flexible, and can adapt to different energy demands or production situations at different time points. The introduction of a spiral model enables the system to better adapt to time dependent variations. It increases the robustness of the system, enabling it to maintain an efficient energy configuration in the face of changing environments and demands.
The oscillation term of the spiral model can help the system explore the potential optimization space. By constantly adjusting the energy configuration and observing the change in performance scores, the system can more fully understand the performance differences between different configurations, thereby more easily finding a new optimal energy configuration. The spiral shape variation of the spiral model helps to reduce the performance score gap between each current energy configuration and the optimal energy configuration. This means that the system tends to be optimally configured more quickly, improving the energy utilization efficiency of the system.
The oscillation term is a mathematical term that is added to the energy configuration of the system. The purpose of this oscillation term is to simulate the periodic and dynamic changes of each energy unit in the system. It may be a periodic function such as a sine wave or a cosine wave, or a mathematical term designed according to the specific needs of the system. By introducing an oscillation term, the energy configuration starts to exhibit periodic or dynamic characteristics. This means that the energy units in the system will change according to the change of the oscillation term, resulting in the generation of a dynamic result. This dynamic result is a snapshot of the energy configuration of the system during simulation time. Once the dynamic results are obtained, the system may perform a random search to find a new optimal energy configuration. Random search is an optimization method that evaluates its performance by randomly selecting different energy configurations. This can help the system explore widely in the configuration space to find potentially optimal solutions. During the random search, the system will evaluate the performance of each randomly generated energy configuration, typically using the previously defined objective function. When a configuration with a higher performance score is found, it is considered a new optimal energy configuration. This process is iterated continuously to gradually improve the energy configuration. By introducing an oscillation term, the system is able to better simulate the periodicity and dynamics in an actual system, such as weather changes or load fluctuations. This helps the system to more accurately reflect changes in the actual environment, thereby better optimizing the energy configuration. Random search is a powerful tool for discovering new solutions. It allows the system to explore widely in the configuration space to find the best possible energy configuration. This is very useful for coping with complex energy systems and uncertainties. By continually performing random searches and calculating new optimal configurations, the system can continually improve the energy configuration to accommodate changing demands and environmental conditions. This helps to improve the performance and energy utilization efficiency of the system.
Example 2: the energy source is configured as a data set comprising a plurality of different categories of configuration parameters.
Specifically, the energy configuration is first represented as a data set. This data set may include a variety of different energy configurations, and these configuration parameters may include various metrics of energy type, energy production, energy storage capacity, efficiency, and the like. Each configuration is represented as one data point in the data set. Configuration parameters may be divided into different categories, which may include physical parameters (such as area and orientation of solar panels), economic parameters (such as energy price and cost), environmental parameters (such as meteorological data and environmental impact assessment), and the like. These different classes of parameters may provide a versatile information for analysis and optimization of energy configurations. Different kinds of configuration parameters are integrated together to obtain more comprehensive energy configuration information. This helps the system better understand and evaluate the performance, cost, and environmental impact aspects of each configuration. The energy configuration data set may be used for data analysis and optimization. By analyzing this data, it is possible to identify which configurations perform best in certain situations and which may require improvement. The optimization algorithm can use this data to find the optimal energy configuration to meet different objectives, such as maximizing energy production, reducing costs, or reducing environmental impact.
Example 3: initialization model of the energy unitThe expression is used as follows:
；
wherein,indicate->The initialization model of each energy unit characterizes the initial energy configuration of the energy unit; />Is a time variable; />A weighted value representing a minimum set of parameters of the energy configuration of the energy unit; />A weighted value representing a maximum set of parameters of the energy configuration of the energy unit; the energy source configuration of each energy source unit is provided with a weighting coefficient matched with the energy source unit corresponding to each category of parameters; weighting value of maximum parameter set of energy configuration +.>Each maximum parameter in the maximum parameter set equal to the energy configuration is multiplied by a corresponding weighting coefficient to obtain a weighting value, and then the weighting values corresponding to all other maximum parameters are added and calculated; minimum parameter set for energy configurationWeighting value->Each minimum parameter in the minimum parameter set equal to the energy configuration is multiplied by the corresponding weighting coefficient to obtain a weighting value, then adding the weighted values corresponding to all other minimum parameters, and calculating to obtain the final product; />For generating a random number between 0 and 1, introducing randomness of the initial state; />Representing the influence of a periodic factor, +.>For amplitude, the intensity of the periodicity factor, +.>For frequency +.>For the phase, determining a point in time at which a periodic factor begins to affect the system; />Representing a nonlinear decay term for modeling thermodynamic and mechanical property changes of a system, wherein +.>An initial intensity representing a nonlinear decay; />Indicating the rate of decay; />And->Are index of subscripts, and->For the circumference ofTotal number of period factors>Is the total number of nonlinear decay terms.
In particular, the method comprises the steps of,indicate->Initialization model of individual energy units: this is a time +.>Representing the energy configuration of the energy unit at different points in time. The initialization model is used to describe the initial state of the energy unit, and is a dynamic model that can change over time. />And->: these values represent weighted values of the minimum and maximum parameter sets of the energy configuration of the energy unit. The minimum parameter set contains the minimum parameters of the energy configuration, while the maximum parameter set contains the maximum parameters. The weighting values of these parameter sets depend on the weighting coefficients associated with each energy unit, reflecting the importance of the different parameters to the energy configuration. Random item->: this term introduces randomness by generating a random number between 0 and 1, multiplying it by the difference between the maximum and minimum parameter sets, to introduce uncertainty in the initial state. The randomness is to simulate the randomness and uncontrollability that the initial state of the energy unit may have. />: this part represents the influence of the periodicity factor. Comprises->A periodicity factor, each factor consisting of amplitude +.>Frequency->And phase->And (5) determining. These factors simulate periodic changes in the system, such as daily changes in solar radiation. The amplitude determines the intensity of the periodic factor, the frequency determines the frequency of the periodic variation, and the phase determines the start time of the periodic variation. />: this section represents the nonlinear decay term used to model thermodynamic and mechanical property changes of the system. Comprises->A nonlinear decay term, each term consisting of an initial intensityAnd decay Rate->And (5) determining. These terms are used to account for non-linear changes in the system that may occur over time, such as thermal losses or equipment degradation.
Introducing random termsThe randomness of the initial state of the energy unit is simulated, as in practical cases there may be some uncertainty in the initial state. By->The effect of periodic factors, such as daily changes in solar radiation, was simulated. This helps to more accurately reflect the effects of the periodic variations to which the system is subjectedAnd (5) sounding. By->Nonlinear behavior of the system, such as thermal losses or degradation of the device, is taken into account. This helps to more fully account for variations in energy configuration over time.
In the formulaThe initial state of each energy unit at different points in time is shown, which is important for modeling of the energy system. The initial state includes an initial energy configuration of the energy unit that can affect the performance and efficiency of the system. By this formula, the initial state of the system over time can be modeled and recorded. Random item->The randomness is introduced so that the initial state of each energy unit has certain randomness. This reflects the uncertainty and variability of the initial state in the actual system. Taking into account uncertainty helps model system behavior more realistically. In the formulaPartly for modeling the influence of periodicity factors. This is useful for systems that take into account periodic factors such as solar radiation. The amplitude, frequency and phase parameters may be adjusted to simulate different types of periodic variations. +.>And part represents a nonlinear decay term used to model thermodynamic and mechanical property changes of the system. This may help capture nonlinear behavior of the system over time, such as degradation of the device or thermal losses. This formula combines randomness, periodicity factors, and nonlinear decay terms so that the impact of multiple factors on the energy configuration can be considered. This helps to more fully understand and describe the initial state of the energy unit, and how it changes over time. This formula can be used not only to simulate the initial state of the energy unit, but also as a starting point for optimization and analysis.By introducing an optimization algorithm or analysis method on this basis, the energy configuration can be further improved to meet different performance objectives, such as maximizing energy production or reducing costs.
Example 4: the objective function is expressed using the following formula:
；
wherein,indicate->An objective function of the individual energy units having a value of +.>Performance scores for individual energy units; />Indicate->The individual energy units use->The energy source is configured at the time->The output of the energy source; />Is an attenuation factor; />Represents a penalty function when->Any configuration parameter in the energy configuration does not meet the corresponding set threshold range, the penalty function calculates the minimum difference between the configuration parameter and the threshold range,then calculating the ratio of the minimum difference value to the configuration parameter; />Representing the time-varying frequency, and representing the time-varying threshold range.
In particular, the method comprises the steps of,representing an objective function: the value of this function is used to evaluate +.>Performance scores for individual energy units. It is a complex combination function that comprehensively considers a number of factors to evaluate the performance of the energy unit.: this term represents the time integral for taking into account the energy output of the energy unit at different points in time. />Indicate->The individual energy units are at the time->Use of->And (5) energy output quantity of energy configuration. Index item->Attenuation factor->For taking into account the weight of time. The energy output at an earlier point in time has a greater impact on the objective function, while the impact gradually decreases over time. />: this term represents a series of timesAnd the sum of the intermediate points is used for considering whether the configuration parameters meet the punishment of the threshold range. />Represents a penalty function when->When any parameter in the energy configuration does not meet the corresponding set threshold range, the energy configuration calculates the minimum difference value between the configuration parameter and the threshold range, and then calculates the ratio of the minimum difference value to the configuration parameter. />Representing the time-varying frequency, and representing the time-varying threshold range. This can be used to take into account the variation of the threshold range at different points in time.
Time integral term:the energy output of the energy unit at different points in time is taken into account. The exponential term introduces a decay factor to account for the weight of time, making earlier time points more influential on performance scores. Penalty term: />A penalty is taken into account whether the configuration parameters meet a threshold range. If any of the parameters is not within the threshold, a corresponding penalty will be calculated. This may prevent configuration parameters from deviating from the set requirements. The purpose of this objective function is to find an energy configuration such that the energy output of the energy unit at different points in time is maximized and the configuration parameters meet the requirements of the threshold range as much as possible. By adjusting the energy configuration, one can attempt to optimize the value of the objective function to obtain a higher performance score. This formula integrates several aspects of time, energy output and configuration parameters to comprehensively evaluate the performance of the energy unit.
Example 5: the collaborative optimization unit is used for traversing all possible energy configurations by adopting the following formula, calculating the performance scores of the energy units under each energy configuration, and when the performance scores are determined to be optimal, taking the energy configuration corresponding to the energy units as the optimal energy configuration of the energy units:
；
wherein,representing an optimal energy configuration; />Indicate->Weights for a range of thresholds; />Indicate->Midpoint values of the respective threshold ranges; />The number of threshold ranges is equal to the number of types of configuration parameters in the energy configuration.
In particular, the method comprises the steps of,: this is an optimization problem by looking for the parameter +.>To minimize the value of the objective function to determine an optimal energy configuration. The objective function includes two parts: />: this is the objective function mentioned previously for evaluating the performance of the energy unit. The purpose of this section is to maximize the performance of the energy unit. />: this section is used to considerWhether the configuration parameters meet the penalty of the threshold range. />Indicate->Weights of the individual threshold ranges ∈ ->Indicate->The midpoint of the range of thresholds. The deviation of the configuration parameters from the threshold range can be quantified by calculating the 3/2 th power of the distance of the configuration parameters from the midpoint value in the threshold range and then multiplying by the corresponding weight. />: this is indicative of->Weights for a range of thresholds. The weights are used to determine the extent to which deviations of the configuration parameters from the threshold range affect the objective function. Different threshold ranges may have different importance, so their impact may be balanced by weights. />: this is indicative of->The midpoint of the range of thresholds. The midpoint value is typically used to represent a target or desired value for the threshold range. These midpoint values are used in the objective function to calculate the deviation of the configuration parameters from the threshold range.
The objective of the optimization problem is to minimize the objective functionIncluding performance score and threshold range penalty terms. By adjusting the energy source configuration->And (3) searching for the optimal configuration so as to maximize the performance score, and simultaneously, configuring parameters to meet the requirement of a threshold range as far as possible. Penalty term for threshold rangeThe configuration penalty for quantifying the deviation of the configuration parameters from the threshold range will not be met. This ensures that the optimal configuration not only optimizes the performance score, but also considers the validity of the configuration parameters. Weights of different threshold ranges +.>Can be used to balance the importance of different constraints. Higher weights indicate that the threshold range is more stringent and the impact on the configuration is greater.
Example 6: the collaborative optimization unit calculates the difference between the performance scores of the current energy configuration and the optimal energy configuration by adopting the following formula:
；
wherein,indicate->Personal energy configuration and optimal energy configuration +.>A gap between performance scores; />The value range is 1 to 1.3 for the system coefficient; />Is a second order Manhattan norm; />Is a first order Manhattan norm;is->Target values for the respective threshold ranges; reducing the difference between the performance scores of each current energy configuration and the optimal energy configuration by adjusting the current energy configuration until the difference +.>Cannot be reduced, and the first-stage optimization is completed.
In particular, the method comprises the steps of,for measuring +.>Personal energy configuration and optimal energy configuration +.>Gap between performance scores. This gap is a key indicator for measuring the performance of the current configuration relative to the performance of the optimal configuration. />Is a system coefficient, and the value of the system coefficient ranges from 1 to 1.3. This coefficient can influence the gap +.>For adjusting the weight of the performance score. />Representing the second order manhattan norm, also known as euclidean norm. It is used to calculate the second order distance between vectors by summing the squares of the individual element differences and taking the square root. Here, it is used to measure the gap of the performance scoring vector, i.e. +.>Is a difference between the two. />Representing the first order manhattan norm, also known as the manhattan distance. It is used to calculate the first order distance between vectors by summing the absolute values of the individual element differences. Here, it is used to measure the configuration parameter vector and the target value vector +.>Taking into account whether the configuration parameters meet the requirements of the threshold range. />Indicate->Target or desired values for the respective threshold ranges. This is a reference value for measuring whether the configuration parameters meet the threshold range.
Representing the gap between the performance score of the optimal configuration and the performance score of the current configuration. This gap is measured by the Euclidean norm, wherein +.>May be used to adjust the weight of the performance score. The smaller the gap, the closer the current configuration is to the optimal configuration. />Consider whether the configuration parameters meet the requirements of a threshold range. Measuring the difference between each configuration parameter and the target value by first order Manhattan norm and multiplying the difference by the corresponding weight +.>. The purpose of this section is to ensure that the configuration parameters are within the threshold range.
Example 7: an adjustment optimization unit, which uses the following formula to introduce time-dependent dynamic behavior, and simulates each energy unit in the system by adding an oscillation termPeriodically and dynamically changing to obtain dynamic result：
；
Wherein,system coefficients for controlling step size; />Is the intensity of oscillation; />Is the frequency of oscillation; />Is the initial phase of oscillation; />Is the damping coefficient of the oscillation.
In particular, the method comprises the steps of,by adjusting the current energy configuration +.>And the new energy configuration is obtained. This new configuration takes into account the influence of the oscillation term to simulate the dynamic behaviour of the energy unit. />System coefficients for control step size: />Is a system coefficient that is used to control the step size of the adjustment. Greater->The value represents a larger adjustment amplitude and a smaller value/>The value represents a smaller adjustment amplitude. By adjusting->The speed and magnitude of the adjustment can be controlled. />Representing the intensity parameter of the oscillation. Each->The values are used to control the intensity of oscillations of different frequencies. Greater->The value represents a stronger oscillation. />The frequency of the oscillation, i.e. the periodicity of the oscillation, is indicated. Different->The values represent oscillations of different frequencies. Higher->The value indicates that the period of oscillation is shorter. />The initial phase of the oscillation is indicated, which determines the starting position of the oscillation. Different->The values may be such that different oscillation terms are staggered in the time axis, thereby producing different effects.
Is the damping coefficient of oscillation: />Representing the damping coefficient of oscillations, which is controlledThe damping rate of the oscillations is made. Greater->The value indicates that the oscillation decays faster.
Part represents an adjustment term by controlling the step size coefficient +.>To reduce the current energy configuration +.>Performance score gap from optimal configuration>. The purpose of this section is to direct the energy configuration towards better performance, reducing the gap in performance scores. />Representing a superposition of multiple oscillation terms. Each oscillation item consists of oscillation intensity->Oscillation frequency->Initial phase->And oscillation damping coefficient->And (5) controlling. These oscillations simulate the periodic and dynamic changes of each energy unit in the system. Different->、/>、/>And->The values of (2) can be used to simulate oscillations of different frequencies, intensities and decay rates. This helps to accommodate changing demands and conditions in the system for better performance and efficiency.
Example 8: an adjustment optimizing unit for performing random search on the intermediate result by using the following formula, and finding new optimal energy configuration by calculation：
；
Wherein,is indicated at->And->Generating a random configuration therebetween; />Is an adjustment factor; />Is a time decay coefficient; />Is the time frequency.
Specifically, random search is an optimization method that finds the optimal solution by generating random configurations within a given range. The method is based on the probability principle, and by randomly sampling in the configuration space, the configuration with better performance is expected to be found. This is an exploratory approach that is applicable to complex non-linear problems. Time dependent oscillations are a phenomenon that describes the temporal variation of the system. It is ubiquitous in the natural and engineering fields, such as mechanical vibration, signal oscillation in circuits, and the like. These oscillations are typically affected by factors such as amplitude, frequency, phase and attenuation. Performance evaluation of energy configuration is a problem in a multi-dimensional configuration space, where each dimension corresponds to a configuration parameter. Finding the optimal configuration is equivalent to finding the best point of performance in this multidimensional space, but the space can be very complex.
The formula first performs a random search, introducing heuristics by generating a random configuration in the configuration space, in an effort to find a potential, optimal solution that differs from the current configuration. The formula then introduces time dependent oscillation factors that may affect the performance of the configuration. Different oscillation parameters (amplitude, frequency, phase, decay) represent different types of time-dependent behavior, which may originate from dynamic changes inside the system. By adjusting the parameters of the time dependent oscillations, the formula may simulate the dynamic behavior inside the system, which may help the system adapt in a constantly changing environment. The time dependence of the oscillations' intensity, frequency and decay rate control how these oscillations affect the new energy configuration. Finally, random search is combined with time dependent oscillation to find a new optimal energy configuration. This process is performed under the influence of randomness and dynamics, helping to find better performing configurations in complex configuration spaces, adapting to the continual changes in the system.
Example 9: the adjustment optimizing unit is used for adjusting the new optimal energy configuration by using a spiral model to obtain a final optimal energy configuration, and updating the optimal energy configuration into the final optimal energy configuration by using the following formula:
；
wherein,configuring the final optimal energy source; />For the current energy allocation and the optimal energy allocation +.>Is a difference between the initial gap of (2); />An expansion factor that is a spiral shape; />Representing a periodic portion of the spiral path;is the phase of the spiral path; />Is the length of the spiral path; />Is the expansion rate of the helical path.
In particular, the method comprises the steps of,is to adjust the new optimal energy configuration by applying a spiral model +.>And the resulting final configuration. This final configuration is built by a combination of factors including the spiral shape, the periodic portion and the time dependent oscillation term. />Representing the current energy configuration and the optimal energy configuration +.>Initial performance score gap between. This gap is used to adjust the performance of the final configuration to gradually decrease the gap from the optimal configuration. />Representing the expansion factor of the spiral shape, which is used to control the expansion rate of the spiral path. Greater->The value indicates that the spiral path expands faster and smallerThe value indicates that the expansion speed is slow. />Representing a periodic portion of the spiral path that affects the change in energy configuration in a periodic manner. />For the phase of the spiral path, the starting position of the periodic part is controlled. />Representing the length of the spiral path, which determines the overall size of the spiral shape. Greater->The values represent longer spiral paths. />Is the expansion rate parameter of the spiral path, which determines the shape and expansion rate of the spiral path. />Representing a time-dependent oscillation term: this part comprises a superposition of a plurality of time-dependent oscillation terms, each oscillation term consisting of oscillation intensity +.>And attenuation coefficient->And (5) controlling. These oscillation terms simulate the effect of time dependence on energy configuration.Representing a superposition of a plurality of time-dependent oscillation terms: this part comprises a superposition of a plurality of time-dependent oscillation terms, each oscillation term being composed of an amplitude +.>And frequency->And (5) controlling. These oscillation terms simulate the effect of time dependence on energy configuration. />The portion represents the initial performance score gap for controlling the performance of the final configuration. The larger the initial gap, the larger the adjustment amplitude to quickly reduce the performance gap. />For controlling the rate of expansion of the helical path. The expansion of the spiral path can adjust the overall shape of the arrangement to accommodate different requirements. />Part of the periodicity of the spiral path is introduced, which may simulate the effect of periodic variations on the energy configuration. Time-dependent oscillation term [ ]And->) The dynamic impact of time dependence on configuration was simulated.
While specific embodiments of the present invention have been described above, it will be understood by those skilled in the art that these specific embodiments are by way of example only, and that various omissions, substitutions, and changes in the form and details of the methods and systems described above may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the above-described method steps to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is limited only by the following claims.
Claims (6)
1. A distributed energy co-optimization system, the system comprising: a plurality of energy units, each configured with a distributed optimization device; the distributed optimization apparatus includes: the system comprises an energy unit model initializing unit, an objective function constructing unit, a collaborative optimizing unit and an adjusting optimizing unit; the energy unit model initialization unit is used for setting an initialization model for the energy units, and the initialization model of each energy unit characterizes the initial energy configuration of the energy unit; the objective function construction unit is used for constructing an objective function, calculating the performance score of the energy unit according to the initial state of the energy unit, and taking the performance score as the objective of the objective function; the collaborative optimization unit is used for traversing all possible energy configurations, calculating the performance scores of the energy units under each energy configuration, determining the energy configuration corresponding to the energy unit when the performance scores are optimal, serving as the optimal energy configuration of the energy unit, adjusting the current energy configuration according to the optimal energy configuration, reducing the difference between the performance scores of each current energy configuration and the optimal energy configuration, and completing the first-stage optimization; the adjustment optimizing unit is used for introducing time-dependent dynamic behaviors, simulating the periodicity and dynamic changes of each energy unit in the system by adding oscillation items to obtain dynamic results, performing random search on the dynamic results, calculating to find new optimal energy configuration, adjusting the new optimal energy configuration by using a spiral model to obtain final optimal energy configuration, and updating the optimal energy configuration into the final optimal energy configuration;
the adjustment optimizing unit uses the following formula to introduce time-dependent dynamic behavior, and simulate the periodicity and dynamic change of each energy unit in the system by adding an oscillation term to obtain a dynamic result：
；
Wherein,system coefficients for controlling step size; />Is the intensity of oscillation; />Is the frequency of oscillation; />Is the initial phase of oscillation; />Is the damping coefficient of the oscillation;
an adjustment optimizing unit for performing random search on the intermediate result by using the following formula, and finding new optimal energy configuration by calculation：
；
Wherein,is indicated at->And->Generating a random configuration therebetween;is an adjustment factor; />Is a time decay coefficient; />Is the time frequency;
the adjustment optimizing unit is used for adjusting the new optimal energy configuration by using a spiral model to obtain a final optimal energy configuration, and updating the optimal energy configuration into the final optimal energy configuration by using the following formula:
；
wherein,configuring the final optimal energy source; />For the current energy allocation and the optimal energy allocation +.>Is a difference between the initial gap of (2); />An expansion factor that is a spiral shape; />Representing a periodic portion of the spiral path; />Is the phase of the spiral path; />Is the length of the spiral path; />Is the expansion rate of the helical path.
2. The distributed energy co-optimization system of claim 1 wherein the energy source is configured as a data set comprising a plurality of different categories of configuration parameters.
3. The distributed energy co-optimization system of claim 2 wherein the initialization model of the energy unitThe expression is used as follows:
；
wherein,indicate->The initialization model of each energy unit characterizes the initial energy configuration of the energy unit;is a time variable; />A weighted value representing a minimum set of parameters of the energy configuration of the energy unit; />A weighted value representing a maximum set of parameters of the energy configuration of the energy unit; the energy source configuration of each energy source unit is provided with a weighting coefficient matched with the energy source unit corresponding to each category of parameters; weighting value of maximum parameter set of energy configuration +.>Each maximum parameter in the maximum parameter set equal to the energy configuration is multiplied by a corresponding weighting coefficient to obtain a weighting value, and then the weighting values corresponding to all other maximum parameters are added and calculated; weighting value of minimum parameter set of energy configuration +.>Each minimum parameter in the minimum parameter set equal to the energy configuration is multiplied by the corresponding weighting coefficient to obtain a weighting value, then adding the weighted values corresponding to all other minimum parameters, and calculating to obtain the final product;for generating a random number between 0 and 1, introducing randomness of the initial state;representing the influence of a periodic factor, +.>For amplitude, the intensity of the periodicity factor, +.>For frequency +.>For the phase, determining a point in time at which a periodic factor begins to affect the system;representing nonlinear decay terms for modeling thermodynamic and mechanical property changes of a system, whereAn initial intensity representing a nonlinear decay; />Representing attenuationA rate; />And->Are index of subscripts, and->For the total number of periodic factors>Is the total number of nonlinear decay terms.
4. The distributed energy co-optimization system of claim 3 wherein said objective function is expressed using the formula:
；
wherein,indicate->An objective function of the individual energy units having a value of +.>Performance scores for individual energy units; />Indicate->The individual energy units use->The energy source is configured at the time->The output of the energy source;is an attenuation factor; />Represents a penalty function when->If any configuration parameter in the energy configuration does not meet the corresponding set threshold range, calculating the minimum difference value between the configuration parameter and the threshold range by the punishment function, and then calculating the ratio of the minimum difference value to the configuration parameter; />Representing the time-varying frequency, and representing the time-varying threshold range.
5. The distributed energy co-optimization system according to claim 4, wherein the co-optimization unit traverses all possible energy configurations using the following formula, calculates performance scores of the energy units under each energy configuration, and determines an energy configuration corresponding to the energy unit when the performance scores are optimal, as an optimal energy configuration of the energy unit:
；
wherein,representing an optimal energy configuration; />Indicate->Weights for a range of thresholds; />Represent the firstMidpoint values of the respective threshold ranges; />The number of threshold ranges is equal to the number of types of configuration parameters in the energy configuration.
6. The distributed energy co-optimization system of claim 5, wherein the co-optimization unit calculates a performance score gap between the current energy configuration and the optimal energy configuration using the formula:
；
wherein,indicate->Personal energy configuration and optimal energy configuration +.>A gap between performance scores; />The value range is 1 to 1.3 for the system coefficient; />Is a second order Manhattan norm; />Is a first order Manhattan norm;is->Target values for the respective threshold ranges; reducing the difference between the performance scores of each current energy configuration and the optimal energy configuration by adjusting the current energy configuration until the difference +.>Cannot be reduced, and the first-stage optimization is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410032009.4A CN117557067B (en) | 2024-01-10 | 2024-01-10 | Distributed energy collaborative optimization system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410032009.4A CN117557067B (en) | 2024-01-10 | 2024-01-10 | Distributed energy collaborative optimization system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117557067A CN117557067A (en) | 2024-02-13 |
| CN117557067B true CN117557067B (en) | 2024-04-02 |
Family
ID=89823455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410032009.4A Active CN117557067B (en) | 2024-01-10 | 2024-01-10 | Distributed energy collaborative optimization system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557067B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881713A (en) * | 2015-05-22 | 2015-09-02 | 中冶南方工程技术有限公司 | Method for achieving decoupling of optimization algorithm and iron and steel enterprise energy integrated scheduling problem |
| CN110084410A (en) * | 2019-05-31 | 2019-08-02 | 华北电力大学 | A kind of reutilization of the sewage pattern synthesis energy system operation optimization method |
| CN112653188A (en) * | 2021-01-04 | 2021-04-13 | 中国化学工程第六建设有限公司 | Distributed energy system and energy scheduling method |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN115441494A (en) * | 2022-09-21 | 2022-12-06 | 国网山东省电力公司电力科学研究院 | Converter station capacity optimal configuration method and device based on flexible direct current interconnection system |
| CN115600809A (en) * | 2022-10-14 | 2023-01-13 | 国网山西省电力公司太原供电公司（Cn） | Comprehensive energy system optimized scheduling device and method |
| CN116667325A (en) * | 2023-05-29 | 2023-08-29 | 江苏师范大学 | Micro-grid-connected operation optimization scheduling method based on improved cuckoo algorithm |
| CN117013522A (en) * | 2023-07-05 | 2023-11-07 | 国网浙江省电力有限公司嘉兴供电公司 | Comprehensive energy system scheduling optimization method considering distributed power supply and gas-electricity cooperation |
| CN117371755A (en) * | 2023-11-14 | 2024-01-09 | 国网江苏省电力有限公司电力科学研究院 | Multi-microgrid comprehensive energy system distributed optimization method, device, equipment and medium |
| CN117371738A (en) * | 2023-10-25 | 2024-01-09 | 国网浙江省电力有限公司丽水供电公司 | Multi-energy collaborative operation control method and system for village and town comprehensive energy system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9373960B2 (en) * | 2013-03-13 | 2016-06-21 | Oracle International Corporation | Computerized system and method for distributed energy resource scheduling |
| CN103474991B (en) * | 2013-09-18 | 2015-11-18 | 国电南瑞科技股份有限公司 | Based on the power distribution network global optimization dispatching method of time scale |
-
2024
- 2024-01-10 CN CN202410032009.4A patent/CN117557067B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881713A (en) * | 2015-05-22 | 2015-09-02 | 中冶南方工程技术有限公司 | Method for achieving decoupling of optimization algorithm and iron and steel enterprise energy integrated scheduling problem |
| CN110084410A (en) * | 2019-05-31 | 2019-08-02 | 华北电力大学 | A kind of reutilization of the sewage pattern synthesis energy system operation optimization method |
| CN112653188A (en) * | 2021-01-04 | 2021-04-13 | 中国化学工程第六建设有限公司 | Distributed energy system and energy scheduling method |
| US11487273B1 (en) * | 2021-04-30 | 2022-11-01 | Dalian University Of Technology | Distributed industrial energy operation optimization platform automatically constructing intelligent models and algorithms |
| CN115441494A (en) * | 2022-09-21 | 2022-12-06 | 国网山东省电力公司电力科学研究院 | Converter station capacity optimal configuration method and device based on flexible direct current interconnection system |
| CN115600809A (en) * | 2022-10-14 | 2023-01-13 | 国网山西省电力公司太原供电公司（Cn） | Comprehensive energy system optimized scheduling device and method |
| CN116667325A (en) * | 2023-05-29 | 2023-08-29 | 江苏师范大学 | Micro-grid-connected operation optimization scheduling method based on improved cuckoo algorithm |
| CN117013522A (en) * | 2023-07-05 | 2023-11-07 | 国网浙江省电力有限公司嘉兴供电公司 | Comprehensive energy system scheduling optimization method considering distributed power supply and gas-electricity cooperation |
| CN117371738A (en) * | 2023-10-25 | 2024-01-09 | 国网浙江省电力有限公司丽水供电公司 | Multi-energy collaborative operation control method and system for village and town comprehensive energy system |
| CN117371755A (en) * | 2023-11-14 | 2024-01-09 | 国网江苏省电力有限公司电力科学研究院 | Multi-microgrid comprehensive energy system distributed optimization method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 考虑环境因素的分布式能源多目标优化配置;万欣;石孝文;冯俊;;西南师范大学学报(自然科学版);20130520(05);第98-103页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117557067A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dai et al. | A hybrid load forecasting model based on support vector machine with intelligent methods for feature selection and parameter optimization | |
| Ding et al. | Forecasting China's electricity consumption using a new grey prediction model | |
| US8489247B1 (en) | Agent-based chaotic control of wind turbines | |
| CN109659933B (en) | Electric energy quality prediction method for power distribution network with distributed power supply based on deep learning model | |
| Davoodi et al. | A GSO-based algorithm for combined heat and power dispatch problem with modified scrounger and ranger operators | |
| CN105868853B (en) | Method for predicting short-term wind power combination probability | |
| CN104376214A (en) | Fluctuating wind velocity simulation method based on data driving | |
| Ye et al. | Combined approach for short-term wind power forecasting based on wave division and Seq2Seq model using deep learning | |
| Zou et al. | Wind turbine power curve modeling using an asymmetric error characteristic-based loss function and a hybrid intelligent optimizer | |
| Zhang et al. | Short-term load forecasting using recurrent neural networks with input attention mechanism and hidden connection mechanism | |
| Hu et al. | Short-term photovoltaic power prediction based on similar days and improved SOA-DBN model | |
| Wen et al. | Data‐driven transient frequency stability assessment: A deep learning method with combined estimation‐correction framework | |
| Zhang et al. | A novel power‐driven grey model with whale optimization algorithm and its application in forecasting the residential energy consumption in China | |
| CN105719101A (en) | Photovoltaic system power generation power prediction method | |
| CN112149883A (en) | Photovoltaic power prediction method based on FWA-BP neural network | |
| Xu et al. | Multi-cluster based equilibrium optimizer algorithm with compact approach for power system network | |
| Ruan et al. | On vulnerability of renewable energy forecasting: Adversarial learning attacks | |
| Xu et al. | Short-term wind speed prediction based on GRU | |
| Li et al. | Improved shuffled frog leaping algorithm on system reliability analysis | |
| CN117557067B (en) | Distributed energy collaborative optimization system | |
| CN117252288A (en) | Regional resource active support capacity prediction method and system | |
| Dai et al. | A novel long-term prediction model for hemispherical resonator gyroscope's drift data | |
| CN116681154A (en) | Photovoltaic power calculation method based on EMD-AO-DELM | |
| Sun et al. | Aledar: An attentions-based encoder-decoder and autoregressive model for workload forecasting of cloud data center | |
| Pappala et al. | Power system optimization under uncertainties: A PSO approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |